Learning state representations with robotic priors

By Rico Jonschkowski, Oliver Brock. 2015

199 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Unsupervised state representation learning with robotic priors: a robustness benchmark (2017, methodology): “We successfully replicated 2D state results in [1] with sataset 1 (see Table I).”
The limits and potentials of deep learning for robotics (2018, background): “It will then become necessary to reduce the required amount of data by incorporating appropriate priors into learning [49].”
Continual Learning for Robotics (2019, background): “In order to learn robust and adaptive representations with unsupervised learning, the main objective is to find suitable surrogate and meaningful learning signals, as robotics priors (Jonschkowski and Brock, 2015; Lesort et al., 2019), self-supervised models or curiosity driven techniques.”
Loss is its own Reward: Self-Supervision for Reinforcement Learning (2016, background): “The robotic priors of Jonschkowski & Brock (2015) are auxiliary losses for temporal coherence, repeatability, pro-portionality, and causality.”
Deep reinforcement learning with successor features for navigation across similar environments (2016, background): “[27] could potentially further improve our model.”
Regularizing and Optimizing LSTM Language Models (2017, background): “TAR falls under the broad category of slowness regularizers (Hinton, 1989; Földiák, 1991; Luciw & Schmidhuber, 2012; Jonschkowski & Brock, 2015) which penalize the model from producing large changes in the hidden state.”
A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithms (2019, methodology): “Dimensionality reduction and clustering techniques are two common types of unsupervised learning [48, 29, 181].”
Regularizing RNNs by Stabilizing Activations (2015, background): “Unlike the “temporal coherence” penalty of Jonschkowski & Brock (2015), our penalty does not encourage the state representation to remain constant, only its norm .”
Interactive Perception: Leveraging Action in Perception and Perception in Action (2016, methodology): “Jonschkowski and Brock [71] achieve this by introducing a set of hand-defined priors in a loss function that is minimal if the state representation best matches these priors.”
Decoupling feature extraction from policy learning: assessing benefits of state representation learning in goal based robotics (2018, methodology): “Despite good results in mobile robot navigation with a static target (Jonschkowski & Brock, 2015), Robotic Priors are not well suited when the target changes from episode to episode.”
Recent Advances in Robot Learning from Demonstration (2020, methodology): “Unsupervised approaches (87, 88, 89) rely on techniques, such as clustering and dimensionality reduction.”
Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning (2022, background): “…learning objectives that induce invariance to irrelevant factors through the use of domain knowledge about the relevant state features for a task (Jonschkowski and Brock, 2015; Jonschkowski et al., 2017), via data augmentations and contrastive learning (Laskin et al., 2020a), dynamics (Watter et…”
S-RL Toolbox: Environments, Datasets and Evaluation Metrics for State Representation Learning (2018, background): “This knowledge can account for temporal continuity or causality principles that reﬂect the interactions of an agent with its environment (Jonschkowski and Brock, 2015; Jonschkowski et al., 2017).”
Learning Markov State Abstractions for Deep Reinforcement Learning (2021, result): “This approach is similar to the temporal coherence loss proposed by Jonschkowski & Brock (2015).”
Learning Actionable Representations from Visual Observations (2018, methodology): “[12] used similar physics-based robotic-priors to learn state representations”
Lessons from the Amazon Picking Challenge: Four Aspects of Building Robotic Systems (2016, background): “In reinforcement learning, adding explicit knowledge about physics makes the learning problem tractable by reducing its dimensionality [25, 44].”
Contrastive Learning of Structured World Models (2019, background): “…the contrastive objective in Franc¸ois-Lavet et al. (2018), the mutual information objective in Anand et al. (2019), the distribution matching objective in Gelada et al. (2019) or using causality-based losses and physical priors in latent space (Jonschkowski & Brock, 2015; Ehrhardt et al., 2018).”